Evaluating and Understanding Model Editing for Medical Vision Language Models
Model editing promises a fast, targeted way to correct post-deployment mistakes in medical vision-language models (VLMs) without costly retraining. However, existing multimodal model editing benchmarks focus on general-purpose tasks and do not reflect realistic clinical domain requirements and variability. To address this, we introduce M3Bench, a clinically grounded benchmark for multimodal model editing that evaluates whether an edit remains reliable, precise, and generalizable under the challenges of image and text variation, modality and protocol shifts, clinical knowledge composition, and
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%Atomic-man007/Awesome_Multimodel_LLM →
- PossiblePossibly related (embedding) · 53%vlm-starter →
- PossiblePossibly related (embedding) · 50%apanariello4/merge-and-rebase →
- PossiblePossibly related (embedding) · 49%sgl-project/sglang →
- FuzzySimilar title/name (fuzzy) · 59%VioletVision-3B →
“Fuzzy title match (0.73): “Evaluating and Understanding Model Editing for Medical Visio” ≈ “VioletVision-3B””
- LinkedLinked via arxiv author · 85%Guli Zhu →
“Evaluating and Understanding Model Editing for Medical Vision Language Models”
- LinkedLinked via arxiv author · 85%Chenwei Wu →
“Evaluating and Understanding Model Editing for Medical Vision Language Models”
- LinkedLinked via arxiv author · 85%Liyue Shen →
“Evaluating and Understanding Model Editing for Medical Vision Language Models”